CN108038462A - A kind of method and device that Face datection is carried out to real-time video and is identified - Google Patents
A kind of method and device that Face datection is carried out to real-time video and is identified Download PDFInfo
- Publication number
- CN108038462A CN108038462A CN201711403330.5A CN201711403330A CN108038462A CN 108038462 A CN108038462 A CN 108038462A CN 201711403330 A CN201711403330 A CN 201711403330A CN 108038462 A CN108038462 A CN 108038462A
- Authority
- CN
- China
- Prior art keywords
- face
- video
- video data
- characteristic value
- time video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides it is a kind of to real-time video carry out Face datection and identify method and device, the method includes the steps：Real time video data is obtained from front end camera；Real time video data is subjected to hardware decoding, and data conversion is carried out to decoded real time video data, exports yuv video data；Yuv video data are converted to BGR video datas；The face in BGR video datas is detected using deep learning algorithm and extracts characteristic value；Face characteristic value is subjected to hashed, obtains face characteristic cryptographic Hash；Face characteristic cryptographic Hash and the face characteristic cryptographic Hash in the face database that pre-establishes are compared roughly using Hamming distances, the characteristic value of the face in face characteristic value and rough comparison result is then subjected to precise alignment using Euclidean distance；Export comparison result, if human face similarity degree is high, alert；The recognition methods can substitute artificial lookup, effectively save manpower, and instant alarming can be produced after recognizing target face.
Description
Technical field
The present invention relates to a kind of Face datection and the method and device that identifies, refer in particular to it is a kind of to real-time video into pedestrian
The method and device that face is detected and identified.
Background technology
Traditional security protection needs manually to go to browse real-time video, the target person being likely to occur from the lookup in real-time video
Thing, is manually alarmed when finding target person, but more and more wider with the scope of video monitoring, and target person occurs
There is uncertainty in the time of monitoring range, the quantity of the personage occurred in monitor video is large number of, depends merely on and manually goes to look into
Look for the manpower and materials that video pictures target person needs expend also higher and higher, the notice of people is limited, in video pictures number
When more, target person is easily omitted, and sees that video the time it takes cost is also very high again, manually goes out to find target
The reliability of personage is not high, accordingly, it is desirable to provide one kind can to real-time video carry out Face datection and know method for distinguishing and
Device.
The content of the invention
In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention is：It is a kind of that face inspection is carried out to real-time video
Survey and know method for distinguishing, including step,
S10), real time video data is obtained from front end camera；
S20 real time video data), is subjected to hardware decoding, and data conversion is carried out to decoded real time video data,
Export yuv video data；
S30 yuv video data), are converted to BGR video datas；
S40), user's face detection algorithm detection is detected the face in BGR video datas and extracts characteristic value；
S50 face characteristic value), is subjected to hashed, obtains face characteristic cryptographic Hash；
S60 the face characteristic cryptographic Hash in face characteristic cryptographic Hash and the face database pre-established), is used into Hamming distances
Compared roughly, then by the face characteristic value of the face in face characteristic value and rough comparing result using Euclidean distance into
The accurate contrast of row；
S70 comparison result, if human face similarity degree is high, alert), are exported；
The step S10 includes,
S11 the configuration file of front end camera), is read, obtains the configuration information of respective channel；
S12), by pre-configured user name and user cipher, front end camera is logged in；
S13), forward end camera sends the solicited message for obtaining real time video data；
S14 after), front end camera receives solicited message, real time video data is sent；
S15 the video data size to be received), is calculated according to video header, receives the video data of corresponding number；
S16), put the video data received into buffering area pointed by intelligent pointer, be then put into intelligent pointer
Video pointer chained list；
The step S40 includes,
S41), the position coordinates of the number of face in identification video, the position coordinates of face and face key point, institute
Stating face key point includes, left eye, right eye, nose, the left corners of the mouth, the right corners of the mouth；
S42), according to the position coordinates of face and the position coordinates of face key point, picture is cut by affine transformation, is obtained
To face picture；
S43 face characteristic value), is extracted from the face picture using deep learning algorithm；
The step S60 includes,
S61), face characteristic cryptographic Hash is compared roughly with the face characteristic cryptographic Hash in face database using Hamming distances
Right, the threshold value that Hamming distances are less than setting had both been the face characteristic cryptographic Hash for the condition that meets；
S62), face characteristic value is accurately compared with the characteristic value of the face in rough comparison result using Euclidean distance
It is right, if Euclidean distance is less than the threshold value of setting, it is judged as human face similarity degree height.
Further, Face datection is carried out to real-time video and knows method for distinguishing, is further included first with the face of known personage
Picture detects face, then extracts characteristic value, and then hashed obtains feature cryptographic Hash, then characteristic value and feature cryptographic Hash
The step being added into face database.
Further, the configuration information includes IP, user name and the user cipher of front end camera.
Further, the step S20 includes,
S21 hard decoder parameter), is initialized, the picture format of yuv video data is set as I420, decoded video lattice
Formula is set as h264 or h265；
S22 a video decoded instance), is created, the form for decoded real time video data is set；
S23 a Video Quality Metric example), is created, event call-back function is set；
S24), it is hit by a bullet out video intelligent pointer from video pointer chained list, the h264 or h265 that then intelligent pointer is directed toward
Video data is sent into Video decoding module and carries out hard decoder；
S25 resolution ratio scaling), is carried out using ffmpeg to decoded yuv video data.
In order to solve the above-mentioned technical problem, another technical solution for using of the present invention for：It is a kind of to real-time video into pedestrian
The device that face is detected and identified, including,
Real-time video acquisition module, for obtaining real time video data from front end camera；
Video decoding module, for real time video data to be carried out hardware decoding, and to decoded real time video data
Data conversion is carried out, yuv video data is exported, then goes to data conversion module；
Data conversion module, for yuv video data to be converted to BGR video datas, then goes to detection and extracts spy
Value indicative module；
Detect and extract characteristic value module, for user's face detection algorithm detection to the face in BGR video datas into
Row detects and extracts characteristic value, then goes to face characteristic value hashed module；
Face characteristic value hashed module, for face characteristic value to be carried out hashed, obtains face characteristic cryptographic Hash, and
After go to face characteristic value comparing module；
Face characteristic value comparing module, for by the face characteristic in face characteristic cryptographic Hash and the face database that pre-establishes
Cryptographic Hash is compared roughly using Hamming distances, then that the face of the face in face characteristic value and rough comparing result is special
Value indicative is accurately contrasted using Euclidean distance, then goes to result output module；
As a result output module, for exporting comparison result, if human face similarity degree is high, alert；
The real-time video acquisition module includes,
Configuration information acquiring unit, for reading the configuration file of front end camera, obtains the configuration information of respective channel；
Camera logs in unit, for by pre-configured user name and user cipher, logging in front end camera；
Video data request unit, the solicited message for obtaining real time video data is sent for forward end camera；
Front end camera, after receiving solicited message, sends real time video data；
Video reception unit, for calculating the video data size to be received according to video header, receives corresponding number
Video data；
Intelligent pointer unit, for the video data received to be put into the buffering area pointed by intelligent pointer, then will
Intelligent pointer is put into video pointer chained list；
The detection identification module includes,
Face identification unit, for identifying the number of the face in video, the position coordinates of face and face key point
Position coordinates, the face key point includes, left eye, right eye, nose, the left corners of the mouth, the right corners of the mouth, then go to picture cut it is single
Member；
Picture cuts unit, for the position coordinates according to face and the position coordinates of face key point, passes through affine change
Cutting picture is changed, obtains face picture, then goes to face characteristic extraction unit；
Face characteristic extraction unit, for extracting face characteristic value from the face picture using deep learning algorithm；
The face characteristic value comparing module includes,
Hamming distances comparing unit, for face characteristic cryptographic Hash in face characteristic cryptographic Hash and face database to be used hamming
Distance is compared, and the threshold value that Hamming distances are less than setting had both been the face characteristic cryptographic Hash for the condition that meets, was then gone to European
Apart from comparing unit；
Euclidean distance comparing unit, for face characteristic value to be used Europe with the characteristic value of the face in rough comparison result
Formula distance carries out precise alignment, if Euclidean distance is less than the threshold value of setting, is judged as human face similarity degree height.
Further, Face datection and the device identified are carried out to real-time video, further includes face characteristic add module, is used
The face picture detection face of personage known to Yu Xianyong, then extracts characteristic value, and then hashed obtains feature cryptographic Hash, then
Characteristic value and feature cryptographic Hash are added into face database.
Further, the configuration information that the configuration information acquiring unit obtains includes, the IP of front end camera, user name
And user cipher.
Further, the Video decoding module includes,
Parameter initialization unit, for initializing hard decoder parameter, the picture format of yuv video data is set as
I420, decoded video format are set as h264 or h265, then go to decoded instance creating unit；
Decoded instance creating unit, for creating a video decoded instance, decoded real time video data is wanted in setting
Form, then goes to transform instances creating unit；
Transform instances creating unit, for creating a Video Quality Metric example, sets event call-back function, then goes to intelligence
Can pointer pop-up unit；
Intelligent pointer ejects unit, for being hit by a bullet out video intelligent pointer from video pointer chained list, then intelligent pointer
H264 the or h265 video datas of direction are sent into Video decoding module and carry out hard decoder, then go to resolution ratio unit for scaling；
Resolution ratio unit for scaling, for carrying out resolution ratio scaling using ffmpeg to decoded yuv video data.
The beneficial effects of the present invention are：By reading the video data of front end camera, hard decoder is then carried out, is being solved
Video intelligent analysis is carried out after code, face location coordinate is detected by Face datection algorithm, extracts the feature of face key point
Value, is then compared the characteristic value of the face of extraction with the face characteristic value of face database, quickly face can be known
Not, if face and human face similarity degree to be identified that detection recognizes are high, alert.The recognition methods can substitute
Manually search, effectively save manpower, and greatly improve the speed that target person is searched in real-time video.
Brief description of the drawings
The concrete structure of the present invention is described in detail below in conjunction with the accompanying drawings
Fig. 1 is flow chart of the method for the present invention；
Fig. 2 is the device of the invention module frame chart.
Embodiment
In order to describe the technical content, the structural feature, the achieved object and the effect of this invention in detail, below in conjunction with embodiment
And attached drawing is coordinated to be explained in detail.
It is a kind of that Face datection is carried out to real-time video and knows method for distinguishing, including step with reference to figure 1,
S10), real time video data is obtained from front end camera；
S20 real time video data), is subjected to hardware decoding, and data conversion is carried out to decoded real time video data,
Export yuv video data；
S30 yuv video data), are converted to BGR video datas；
S40), user's face detection algorithm detection is detected the face in BGR video datas and extracts characteristic value；
S50 face characteristic value), is subjected to hashed, obtains face characteristic cryptographic Hash；
S60 the face characteristic cryptographic Hash in face characteristic cryptographic Hash and the face database pre-established), is used into Hamming distances
Compared roughly, then by the face characteristic value of the face in face characteristic value and rough comparing result using Euclidean distance into
The accurate contrast of row；
S70 comparison result, if human face similarity degree is high, alert), are exported；
The step S10 includes,
S11 the configuration file of front end camera), is read, obtains the configuration information of respective channel；
S12), by pre-configured user name and user cipher, front end camera is logged in；
S13), forward end camera sends the solicited message for obtaining real time video data；
S14 after), front end camera receives solicited message, real time video data is sent；
S15 the video data size to be received), is calculated according to video header, receives the video data of corresponding number；
S16), put the video data received into buffering area pointed by intelligent pointer, be then put into intelligent pointer
Video pointer chained list；
The step S40 includes,
S41), the position coordinates of the number of face in identification video, the position coordinates of face and face key point, institute
Stating face key point includes, left eye, right eye, nose, the left corners of the mouth, the right corners of the mouth；
S42), according to the position coordinates of face and the position coordinates of face key point, picture is cut by affine transformation, is obtained
To face picture；
S43 face characteristic value), is extracted from the face picture using deep learning algorithm；
The step S60 includes,
S61), face characteristic cryptographic Hash is compared with the face characteristic cryptographic Hash in face database using Hamming distances,
The threshold value that Hamming distances are less than setting had both been the face characteristic cryptographic Hash for the condition that meets；
S62), face characteristic value is accurately compared with the characteristic value of the face in rough comparison result using Euclidean distance
It is right, if Euclidean distance is less than the threshold value of setting, it is judged as human face similarity degree height.
The beneficial effects of the present invention are：By reading the video data of front end camera, hard decoder is then carried out, is being solved
Video intelligent analysis is carried out after code, face location coordinate is detected by Face datection algorithm, extracts the characteristic value of face, then
The characteristic value of the face of extraction is compared with the face characteristic value of face database, quickly face can be identified, if
The human face similarity degree detected in the face and face database recognized is high, then alert.The recognition methods can substitute manually
Search, effectively save manpower, and greatly improve the speed that target person is searched in real-time video.
Embodiment one
Further, Face datection is carried out to real-time video and knows method for distinguishing, is further included first with the face of known personage
Picture detects face, then extracts characteristic value, and then hashed obtains feature cryptographic Hash, then characteristic value and feature cryptographic Hash
The step being added into face database.
By this method, a face database is established, by the characteristic value of face, face characteristic cryptographic Hash is added to face database
In, for carrying out contrast identification with the face in real time video data, the number of the face in face database for one or one with
On, face can be different angle face, can effectively improve the accuracy rate of face characteristic comparison.
Embodiment two
Further, the configuration information includes IP, user name and the user cipher of front end camera.IP address is used for true
Determine the address of camera, user name and user cipher pre-set, it is necessary to when logging in front end camera, be loaded directly into stepping on
Camera is recorded, avoids repeatedly inputting user name and the flow of user cipher.
Embodiment three
Further, the step S20 includes,
S21 hard decoder parameter), is initialized, the picture format of yuv video data is set as I420, decoded video lattice
Formula is set as h264 or h265；
S22 a video decoded instance), is created, the form for decoded real time video data is set；
S23 a Video Quality Metric example), is created, event call-back function is set；
S24), it is hit by a bullet out video intelligent pointer from video pointer chained list, the h264 or h265 that then intelligent pointer is directed toward
Video data is sent into Video decoding module and carries out hard decoder；
S25 resolution ratio scaling), is carried out using ffmpeg to decoded yuv video data.
This method sets decoding parametric, is decoded by the real time video data being directed toward to video intelligent pointer, right
Decoded yuv video data carry out resolution ratio and zoom in and out, and reduce the later stage to shared by video data progress intellectual analysis
Expense (including CPU overhead, GPU expenses).
With reference to figure 2, another technical solution that the present invention uses for：It is a kind of to real-time video carry out Face datection and identify
Device, including,
Real-time video acquisition module, for obtaining real time video data from front end camera；
Video decoding module, for real time video data to be carried out hardware decoding, and to decoded real time video data
Data conversion is carried out, yuv video data is exported, then goes to data conversion module；
Data conversion module, for yuv video data to be converted to BGR video datas, then goes to detection and extracts spy
Value indicative module；
Detect and extract characteristic value module, for user's face detection algorithm detection to the face in BGR video datas into
Row detects and extracts characteristic value, then goes to face characteristic value hashed module；
Face characteristic value hashed module, for face characteristic value to be carried out hashed, obtains face characteristic cryptographic Hash, and
After go to face characteristic value comparing module；
Face characteristic value comparing module, for by the face characteristic in face characteristic cryptographic Hash and the face database that pre-establishes
Cryptographic Hash is compared roughly using Hamming distances, then that the face of the face in face characteristic value and rough comparing result is special
Value indicative is accurately contrasted using Euclidean distance, then goes to result output module；
As a result output module, for exporting comparison result, if human face similarity degree is high, alert；
The real-time video acquisition module includes,
Configuration information acquiring unit, for reading the configuration file of front end camera, obtains the configuration information of respective channel；
Camera logs in unit, for by pre-configured user name and user cipher, logging in front end camera；
Video data request unit, the solicited message for obtaining real time video data is sent for forward end camera；
Front end camera, after receiving solicited message, sends real time video data；
Video reception unit, for calculating the video data size to be received according to video header, receives corresponding number
Video data；
Intelligent pointer unit, for the video data received to be put into the buffering area pointed by intelligent pointer, then will
Intelligent pointer is put into video pointer chained list；
The detection identification module includes,
Face identification unit, for identifying the number of the face in video, the position coordinates of face and face key point
Position coordinates, the face key point includes, left eye, right eye, nose, the left corners of the mouth, the right corners of the mouth, then go to picture cut it is single
Member；
Picture cuts unit, for the position coordinates according to face and the position coordinates of face key point, passes through affine change
Cutting picture is changed, obtains face picture, then goes to face characteristic extraction unit；
Face characteristic extraction unit, for extracting face characteristic value from the face picture using deep learning algorithm；
The face characteristic value comparing module includes,
Hamming distances comparing unit, for face characteristic cryptographic Hash in face characteristic cryptographic Hash and face database to be used hamming
Distance is compared, and the threshold value that Hamming distances are less than setting had both been the face characteristic cryptographic Hash for the condition that meets, was then gone to European
Apart from comparing unit；
Euclidean distance comparing unit, for face characteristic value to be used Europe with the characteristic value of the face in rough comparison result
Formula distance carries out precise alignment, if Euclidean distance is less than the threshold value of setting, is judged as human face similarity degree height.
Video data of the invention by reading front end camera, then carries out hard decoder, carries out video intelligence after the decoding
It can analyze, face location coordinate is detected by Face datection algorithm, extracts the characteristic value of face, it is then that the face of extraction is special
Value indicative is compared with the face characteristic value of face database, and quickly face can be identified, if the face that detection recognizes
It is high with the human face similarity degree in face database, then alert.The recognition methods can substitute artificial lookup, effectively save people
Power, and greatly improve the speed that target person is searched in real-time video.
Example IV
Further, Face datection and the device identified are carried out to real-time video, further includes face characteristic add module, is used
The face picture detection face of personage known to Yu Xianyong, then extracts characteristic value, and then hashed obtains feature cryptographic Hash, then
Characteristic value and feature cryptographic Hash are added into face database.
By this method, a face database is established, by the characteristic value of face, face characteristic cryptographic Hash is added to face database
In, for carrying out contrast identification with the face in real time video data, the number of the face of known personage is one in face database
Or more than one, face can be different angle face, can effectively improve the accuracy rate of face characteristic comparison.
Embodiment five
Further, the configuration information that the configuration information acquiring unit obtains includes, the IP of front end camera, user name
And user cipher.IP address is used for the address for determining camera, and user name and user cipher are pre-set, it is necessary to log in front end
During camera, it is loaded directly into that camera can be logged in, avoids repeatedly inputting user name and the flow of user cipher.
Embodiment six
Further, the Video decoding module includes,
Parameter initialization unit, for initializing hard decoder parameter, the picture format of yuv video data is set as
I420, decoded video format are set as h264 or h265, then go to decoded instance creating unit；
Decoded instance creating unit, for creating a video decoded instance, decoded real time video data is wanted in setting
Form, then goes to transform instances creating unit；
Transform instances creating unit, for creating a Video Quality Metric example, sets event call-back function, then goes to intelligence
Can pointer pop-up unit；
Intelligent pointer ejects unit, for being hit by a bullet out video intelligent pointer from video pointer chained list, then intelligent pointer
H264 the or h265 video datas of direction are sent into Video decoding module and carry out hard decoder, then go to resolution ratio unit for scaling；
Resolution ratio unit for scaling, for carrying out resolution ratio scaling using ffmpeg to decoded yuv video data.
This method sets decoding parametric, and the real time video data being directed toward to video intelligent pointer decodes, to decoding
Yuv video data afterwards carry out resolution ratio and zoom in and out, and it is required to yuv video data progress intellectual analysis to reduce the later stage
CPU overhead and GPU expenses.
The present invention adopts the video data by reading front end camera in summary, and the video data of reading, which is put into, intelligently to be referred to
Buffering area pointed by pin, to intelligent pointer be directed toward real time video data decode, to decoded yuv video data into
Row resolution ratio zooms in and out, and the reduction later stage carries out yuv video data the required CPU overhead of intellectual analysis and GPU expenses,
Video intelligent analysis is carried out after decoding, face location coordinate is detected by Face datection algorithm, extracts the characteristic value of face, so
The face characteristic value of extraction is compared with the face characteristic value of face database afterwards, quickly face can be identified, if
The human face similarity degree detected in the face and face database recognized is high, then alert.The recognition methods can substitute manually
Search, effectively save manpower, and greatly improve the speed that target person is searched in real-time video.
The foregoing is merely the embodiment of the present invention, is not intended to limit the scope of the invention, every to utilize this hair
The equivalent structure or equivalent flow shift that bright specification and accompanying drawing content are made, is directly or indirectly used in other relevant skills
Art field, is included within the scope of the present invention.
Claims (8)
1. a kind of carry out Face datection to real-time video and know method for distinguishing, it is characterised in that：Including step,
S10), real time video data is obtained from front end camera；
S20 real time video data), is subjected to hardware decoding, and data conversion, output are carried out to decoded real time video data
Yuv video data；
S30 yuv video data), are converted to BGR video datas；
S40), user's face detection algorithm detection is detected the face in BGR video datas and extracts characteristic value；
S50 face characteristic value), is subjected to hashed, obtains face characteristic cryptographic Hash；
S60), face characteristic cryptographic Hash and the face characteristic cryptographic Hash in the face database that pre-establishes are carried out using Hamming distances
It is rough to compare, the face characteristic value of the face in face characteristic value and rough comparing result is then subjected to essence using Euclidean distance
Really contrast；
S70 comparison result, if human face similarity degree is high, alert), are exported；
The step S10 includes,
S11 the configuration file of front end camera), is read, obtains the configuration information of respective channel；
S12), by pre-configured user name and user cipher, front end camera is logged in；
S13), forward end camera sends the solicited message for obtaining real time video data；
S14 after), front end camera receives solicited message, real time video data is sent；
S15 the video data size to be received), is calculated according to video header, receives the video data of corresponding number；
S16), put the video data received into buffering area pointed by intelligent pointer, intelligent pointer is then put into video
Pointer chained list；
The step S40 includes,
S41), the position coordinates of the number of face in identification video, the position coordinates of face and face key point, the people
Face key point includes, left eye, right eye, nose, the left corners of the mouth, the right corners of the mouth；
S42), according to the position coordinates of face and the position coordinates of face key point, picture is cut by affine transformation, obtains people
Face picture；
S43 face characteristic value), is extracted from the face picture using deep learning algorithm；
The step S60 includes,
S61), face characteristic cryptographic Hash is compared with the face characteristic cryptographic Hash in face database using Hamming distances, hamming
The threshold value that distance is less than setting had both been the face characteristic cryptographic Hash for the condition that meets；
S62 face characteristic value), is subjected to precise alignment with the characteristic value of the face in rough comparison result using Euclidean distance,
If Euclidean distance is less than the threshold value of setting, it is judged as human face similarity degree height.
2. Face datection is carried out to real-time video as claimed in claim 1 and knows method for distinguishing, it is characterised in that：Further include elder generation
Face is detected with the face picture of known personage, then extracts characteristic value, then hashed obtains feature cryptographic Hash, then feature
Value and feature cryptographic Hash are added into the step in face database.
3. Face datection is carried out to real-time video as claimed in claim 1 and knows method for distinguishing, it is characterised in that：The configuration
Information includes IP, user name and the user cipher of front end camera.
4. Face datection is carried out to real-time video as claimed in claim 1 and knows method for distinguishing, it is characterised in that：The step
S20 includes,
S21 hard decoder parameter), is initialized, the picture format of yuv video data is set as I420, decoded video format is set
It is set to h264 or h265；
S22 a video decoded instance), is created, the form for decoded real time video data is set；
S23 a Video Quality Metric example), is created, event call-back function is set；
S24), it is hit by a bullet out video intelligent pointer from video pointer chained list, h264 the or h265 videos that then intelligent pointer is directed toward
Data are sent into Video decoding module and carry out hard decoder；
S25 resolution ratio scaling), is carried out using ffmpeg to decoded yuv video data.
A kind of 5. device that Face datection is carried out to real-time video and is identified, it is characterised in that：Including,
Real-time video acquisition module, for obtaining real time video data from front end camera；
Video decoding module, for real time video data to be carried out hardware decoding, and carries out decoded real time video data
Data conversion, exports yuv video data, then goes to data conversion module；
Data conversion module, for yuv video data to be converted to BGR video datas, then goes to detection and extracts characteristic value
Module；
Detect and extract characteristic value module, the face in BGR video datas is examined for the detection of user's face detection algorithm
Survey and extract characteristic value, then go to face characteristic value hashed module；
Face characteristic value hashed module, for face characteristic value to be carried out hashed, obtains face characteristic cryptographic Hash, then turns
To face characteristic value comparing module；
Face characteristic value comparing module, for by the face characteristic Hash in face characteristic cryptographic Hash and the face database that pre-establishes
Value is compared roughly using Hamming distances, then by the face characteristic value of the face in face characteristic value and rough comparing result
Accurately contrasted using Euclidean distance, then go to result output module；
As a result output module, for exporting comparison result, if human face similarity degree is high, alert；
The real-time video acquisition module includes,
Configuration information acquiring unit, for reading the configuration file of front end camera, obtains the configuration information of respective channel；
Camera logs in unit, for by pre-configured user name and user cipher, logging in front end camera；
Video data request unit, the solicited message for obtaining real time video data is sent for forward end camera；
Front end camera, after receiving solicited message, sends real time video data；
Video reception unit, for calculating the video data size to be received according to video header, receives regarding for corresponding number
Frequency evidence；
Intelligent pointer unit, then will intelligence for the video data received to be put into the buffering area pointed by intelligent pointer
Pointer is put into video pointer chained list；
The detection identification module includes,
Face identification unit, for identifying the position of the number of the face in video, the position coordinates of face and face key point
Coordinate is put, the face key point includes, left eye, right eye, nose, the left corners of the mouth, the right corners of the mouth, then goes to picture and cuts unit；
Picture cuts unit, for the position coordinates according to face and the position coordinates of face key point, is cut out by affine transformation
Picture is cut, obtains face picture, then goes to face characteristic extraction unit；
Face characteristic extraction unit, for extracting face characteristic value from the face picture using deep learning algorithm；
The face characteristic value comparing module includes,
Hamming distances comparing unit, for face characteristic cryptographic Hash in face characteristic cryptographic Hash and face database to be used Hamming distances
Compared roughly, the threshold value that Hamming distances are less than setting had both been the face characteristic cryptographic Hash for the condition that meets, was then gone to European
Apart from comparing unit；
Euclidean distance comparing unit, for by face characteristic value with the face in rough comparison result characteristic value using it is European away from
From precise alignment is carried out, if Euclidean distance is less than the threshold value of setting, it is judged as human face similarity degree height.
6. Face datection and the device identified are carried out to real-time video as claimed in claim 5, it is characterised in that：Further include people
Face feature add module, for first detecting face with the face picture of known personage, then extracts characteristic value, then hashed obtains
It is added into feature cryptographic Hash, then characteristic value and feature cryptographic Hash in face database.
7. Face datection and the device identified are carried out to real-time video as claimed in claim 5, it is characterised in that：The configuration
The configuration information that information acquisition unit obtains includes, IP, user name and the user cipher of front end camera.
8. Face datection and the device identified are carried out to real-time video as claimed in claim 5, it is characterised in that：The video
Decoder module includes,
Parameter initialization unit, for initializing hard decoder parameter, is set as I420 by the picture format of yuv video data, solution
The video format of code is set as h264 or h265, then goes to decoded instance creating unit；
Decoded instance creating unit, for creating a video decoded instance, sets the form for wanting decoded real time video data,
Then go to transform instances creating unit；
Transform instances creating unit, for creating a Video Quality Metric example, sets event call-back function, then goes to and intelligently refer to
Pin ejects unit；
Intelligent pointer ejects unit, and for being hit by a bullet out video intelligent pointer from video pointer chained list, then intelligent pointer is directed toward
H264 or h265 video datas be sent into Video decoding module carry out hard decoder, then go to resolution ratio unit for scaling；
Resolution ratio unit for scaling, for carrying out resolution ratio scaling using ffmpeg to decoded yuv video data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711403330.5A CN108038462A (en) | 2017-12-22 | 2017-12-22 | A kind of method and device that Face datection is carried out to real-time video and is identified |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711403330.5A CN108038462A (en) | 2017-12-22 | 2017-12-22 | A kind of method and device that Face datection is carried out to real-time video and is identified |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108038462A true CN108038462A (en) | 2018-05-15 |
Family
ID=62100430
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711403330.5A Pending CN108038462A (en) | 2017-12-22 | 2017-12-22 | A kind of method and device that Face datection is carried out to real-time video and is identified |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108038462A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108769581A (en) * | 2018-05-24 | 2018-11-06 | 南京邮电大学 | A kind of vehicle-carried mobile monitoring system towards public service |
| CN109214358A (en) * | 2018-09-30 | 2019-01-15 | 天津天地伟业电子工业制造有限公司 | A method of Image Acquisition detection is carried out by USB camera |
| CN109446946A (en) * | 2018-10-15 | 2019-03-08 | 浙江工业大学 | A kind of multi-cam real-time detection method based on multithreading |
| CN109783692A (en) * | 2019-01-08 | 2019-05-21 | 深圳英飞拓科技股份有限公司 | The target signature code comparison method and device that a kind of fast data and slow data combine |
| CN115553709A (en) * | 2022-10-28 | 2023-01-03 | 南京尚哲智能科技有限公司 | Automatic intelligent vision detection system and method |
| CN115859247A (en) * | 2023-02-20 | 2023-03-28 | 中国信息通信研究院 | Password security verification method and device, electronic equipment and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104394460A (en) * | 2014-11-24 | 2015-03-04 | 深圳市华宝电子科技有限公司 | Audio-video file locating method and device |
| CN105046217A (en) * | 2015-07-06 | 2015-11-11 | 江苏先发信息科技有限公司 | Face recognition large data amount concurrency scheme processing method |
| CN105979218A (en) * | 2016-06-13 | 2016-09-28 | 中南大学 | High-definition real-time monitoring video efficient transmission method |
| CN106169067A (en) * | 2016-07-01 | 2016-11-30 | 恒东信息科技无锡有限公司 | A kind of police dynamic human face of high flux gathers comparison method and system |
| CN107341507A (en) * | 2017-06-20 | 2017-11-10 | 华中科技大学 | A kind of rapid image SIFT feature matching process based on GPU with cascade Hash |
-
2017
- 2017-12-22 CN CN201711403330.5A patent/CN108038462A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104394460A (en) * | 2014-11-24 | 2015-03-04 | 深圳市华宝电子科技有限公司 | Audio-video file locating method and device |
| CN105046217A (en) * | 2015-07-06 | 2015-11-11 | 江苏先发信息科技有限公司 | Face recognition large data amount concurrency scheme processing method |
| CN105979218A (en) * | 2016-06-13 | 2016-09-28 | 中南大学 | High-definition real-time monitoring video efficient transmission method |
| CN106169067A (en) * | 2016-07-01 | 2016-11-30 | 恒东信息科技无锡有限公司 | A kind of police dynamic human face of high flux gathers comparison method and system |
| CN107341507A (en) * | 2017-06-20 | 2017-11-10 | 华中科技大学 | A kind of rapid image SIFT feature matching process based on GPU with cascade Hash |
Non-Patent Citations (2)
| Title |
|---|
| 严严 等.: "基于深度学习的人脸分析研究进展", 《厦门大学学报（自然科学版）》 * |
| 李慧贞 等.: "基于WinCE6.0智能手机视频监控终端软件设计", 《计算机测量与控制》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108769581A (en) * | 2018-05-24 | 2018-11-06 | 南京邮电大学 | A kind of vehicle-carried mobile monitoring system towards public service |
| CN109214358A (en) * | 2018-09-30 | 2019-01-15 | 天津天地伟业电子工业制造有限公司 | A method of Image Acquisition detection is carried out by USB camera |
| CN109446946A (en) * | 2018-10-15 | 2019-03-08 | 浙江工业大学 | A kind of multi-cam real-time detection method based on multithreading |
| CN109446946B (en) * | 2018-10-15 | 2022-03-18 | 浙江工业大学 | Multi-camera real-time detection method based on multithreading |
| CN109783692A (en) * | 2019-01-08 | 2019-05-21 | 深圳英飞拓科技股份有限公司 | The target signature code comparison method and device that a kind of fast data and slow data combine |
| CN109783692B (en) * | 2019-01-08 | 2021-12-31 | 深圳英飞拓科技股份有限公司 | Target feature code comparison method and device combining fast data with slow data |
| CN115553709A (en) * | 2022-10-28 | 2023-01-03 | 南京尚哲智能科技有限公司 | Automatic intelligent vision detection system and method |
| CN115859247A (en) * | 2023-02-20 | 2023-03-28 | 中国信息通信研究院 | Password security verification method and device, electronic equipment and readable storage medium |
| CN115859247B (en) * | 2023-02-20 | 2023-08-15 | 中国信息通信研究院 | Password security verification method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108038462A (en) | A kind of method and device that Face datection is carried out to real-time video and is identified | |
| CN109344787B (en) | Specific target tracking method based on face recognition and pedestrian re-recognition | |
| CN110008797B (en) | Multi-camera multi-face video continuous acquisition method | |
| CN105550257B (en) | A kind of audio/video fingerprint recognition methods and a kind of tamper resistant systems based on audio/video fingerprint Streaming Media | |
| Deniz et al. | Fast violence detection in video | |
| CN105681898B (en) | A kind of detection method and device of similar video and pirate video | |
| CN105574506A (en) | Intelligent face tracking system and method based on depth learning and large-scale clustering | |
| CN105590097B (en) | Dual camera collaboration real-time face identification security system and method under the conditions of noctovision | |
| Avgerinakis et al. | Recognition of activities of daily living for smart home environments | |
| CN105681899B (en) | A kind of detection method and device of similar video and pirate video | |
| WO2019071664A1 (en) | Human face recognition method and apparatus combined with depth information, and storage medium | |
| US8266174B2 (en) | Behavior history retrieval apparatus and behavior history retrieval method | |
| CN105069408A (en) | Video portrait tracking method based on human face identification in complex scenario | |
| CN107153820A (en) | A kind of recognition of face and movement locus method of discrimination towards strong noise | |
| US20090290752A1 (en) | Method for producing video signatures and identifying video clips | |
| CN108364374A (en) | Face access control device based on deep learning and method | |
| CN107977656A (en) | A kind of pedestrian recognition methods and system again | |
| CN108282460B (en) | Evidence chain generation method and device for network security event | |
| CN106454385B (en) | Video frame altering detecting method | |
| CN111767823A (en) | Sleeping post detection method, device, system and storage medium | |
| Raghavendra et al. | Robust 2D/3D face mask presentation attack detection scheme by exploring multiple features and comparison score level fusion | |
| CN108052915A (en) | A kind of method and device that Face datection is carried out to video and is identified | |
| CN111144260A (en) | Detection method, device and system of crossing gate | |
| CN113554682B (en) | Target tracking-based safety helmet detection method | |
| Wanjale et al. | Use of haar cascade classifier for face tracking system in real time video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180515 |